mcpbeat Sign in

Changelog Agent Skill

Maintain Wassette's Keep a Changelog-style CHANGELOG.md by reviewing a focused change, deciding whether it affects users, and updating the [Unreleased] section with concise, categorized, non-duplicate entries.

852 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
931
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/microsoft/wassette --skill changelog

What it tells the agent to use

found in the instruction text
Bash runs shell commands — read the instruction before connecting

The instruction itself

7 sections, as written by the author

changelog skill

Maintain CHANGELOG.md as part of every user-facing Wassette change. Prefer a

small, accurate entry over a commit-log summary.

Workflow

  • Read AGENTS.md and the [Unreleased] section of CHANGELOG.md.
  • Inspect only the change being documented:
  • Use the user-provided diff, pull request, or commit range when available.
  • On a pull request branch, compare against the merge base with main.
  • Otherwise inspect staged and unstaged changes without including unrelated

worktree changes.

  • Decide whether users, operators, component authors, or downstream

integrators can observe the change.

  • Update the existing [Unreleased] section, deduplicating against existing

entries.

  • Review the final diff for placement, duplication, formatting, and scope.

What needs an entry

Add an entry for:

  • New features, commands, options, APIs, integrations, examples, and supported

platforms.

  • Behavior changes, defaults, compatibility changes, and breaking changes.
  • Deprecations and removals.
  • User-visible bug fixes.
  • Security fixes. Avoid unnecessary disclosure before coordinated release.
  • Significant installation, deployment, component-publishing, or operational

changes.

An entry is usually unnecessary for tests, internal refactors, formatting,

comments, routine dependency maintenance, and CI-only changes that do not alter

the delivered product. For such pull requests, use the skip-changelog label.

When relevance is genuinely ambiguous, ask rather than guessing.

Categories

Use these Keep a Changelog headings in this order:

  • Added
  • Changed
  • Deprecated
  • Removed
  • Fixed
  • Security

Reuse an existing heading when possible. Add a missing heading only when the

entry needs it.

Writing entries

  • Write one concise bullet describing the resulting user impact.
  • Match the surrounding voice, punctuation, capitalization, and terminology.
  • Mention breaking behavior explicitly with BREAKING CHANGE.
  • Combine tightly related changes into one entry.
  • Do not duplicate an existing [Unreleased] entry.
  • Add a pull request link only when its number is known, using

(#N).

  • Do not invent a pull request number or leave a placeholder.

Wassette release rules

  • Edit only the current [Unreleased] section.
  • Do not add a version or release date; release.yml owns that transition.
  • Do not rewrite historical releases unless the user explicitly requests a

correction.

  • Do not include routine dependency bumps unless they fix a user-visible issue,

change compatibility, or address a security advisory.

Validation checklist

  • The entry is inside [Unreleased], before the first released version.
  • The category matches the type of user impact.
  • The wording is understandable without reading the implementation diff.
  • Existing headings, blank lines, links, and historical releases are preserved.
  • The diff contains no unrelated changelog edits.
  • If no entry was needed, report that the pull request needs the

skip-changelog label.

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take microsoft/changelog from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.